🍻 cheers
Browse files- README.md +2 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan01_06-59-39_a0707a466317/events.out.tfevents.1704113310.a0707a466317.8840.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +807 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# id1
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6181
|
| 21 |
- Accuracy: 0.6535
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 16 |
|
| 17 |
# id1
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the sooks/id1 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6181
|
| 22 |
- Accuracy: 0.6535
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.6535040710028017,
|
| 4 |
+
"eval_loss": 0.6181166768074036,
|
| 5 |
+
"eval_runtime": 365.5073,
|
| 6 |
+
"eval_samples_per_second": 145.499,
|
| 7 |
+
"eval_steps_per_second": 18.188,
|
| 8 |
+
"total_flos": 1.40117450989583e+20,
|
| 9 |
+
"train_loss": 0.6729164371932674,
|
| 10 |
+
"train_runtime": 20561.1299,
|
| 11 |
+
"train_samples_per_second": 87.94,
|
| 12 |
+
"train_steps_per_second": 5.496
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.6535040710028017,
|
| 4 |
+
"eval_loss": 0.6181166768074036,
|
| 5 |
+
"eval_runtime": 365.5073,
|
| 6 |
+
"eval_samples_per_second": 145.499,
|
| 7 |
+
"eval_steps_per_second": 18.188
|
| 8 |
+
}
|
runs/Jan01_06-59-39_a0707a466317/events.out.tfevents.1704113310.a0707a466317.8840.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab5f2c784e1a2a2f754429a62d283a722048dd27bdfebf50efbdcb7d33a8993a
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 1.40117450989583e+20,
|
| 4 |
+
"train_loss": 0.6729164371932674,
|
| 5 |
+
"train_runtime": 20561.1299,
|
| 6 |
+
"train_samples_per_second": 87.94,
|
| 7 |
+
"train_steps_per_second": 5.496
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,807 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6181166768074036,
|
| 3 |
+
"best_model_checkpoint": "./id1/checkpoint-110000",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 10000,
|
| 6 |
+
"global_step": 113010,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 0.00019823024511105212,
|
| 14 |
+
"loss": 0.6956,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 0.0001964622599769932,
|
| 20 |
+
"loss": 0.6938,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.16,
|
| 25 |
+
"learning_rate": 0.0001946925050880453,
|
| 26 |
+
"loss": 0.6937,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 0.00019292275019909742,
|
| 32 |
+
"loss": 0.6935,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.27,
|
| 37 |
+
"learning_rate": 0.00019115299531014955,
|
| 38 |
+
"loss": 0.6933,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 0.0001893832404212017,
|
| 44 |
+
"loss": 0.6932,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.37,
|
| 49 |
+
"learning_rate": 0.00018761525528714274,
|
| 50 |
+
"loss": 0.6933,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.42,
|
| 55 |
+
"learning_rate": 0.00018584550039819485,
|
| 56 |
+
"loss": 0.6933,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.48,
|
| 61 |
+
"learning_rate": 0.000184075745509247,
|
| 62 |
+
"loss": 0.6933,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.53,
|
| 67 |
+
"learning_rate": 0.0001823059906202991,
|
| 68 |
+
"loss": 0.6933,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.53,
|
| 73 |
+
"eval_accuracy": 0.5007803538857862,
|
| 74 |
+
"eval_loss": 0.6931997537612915,
|
| 75 |
+
"eval_runtime": 359.7161,
|
| 76 |
+
"eval_samples_per_second": 147.842,
|
| 77 |
+
"eval_steps_per_second": 18.481,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.58,
|
| 82 |
+
"learning_rate": 0.00018053800548624015,
|
| 83 |
+
"loss": 0.6933,
|
| 84 |
+
"step": 11000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.64,
|
| 88 |
+
"learning_rate": 0.0001787682505972923,
|
| 89 |
+
"loss": 0.6933,
|
| 90 |
+
"step": 12000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.69,
|
| 94 |
+
"learning_rate": 0.00017700026546323337,
|
| 95 |
+
"loss": 0.6932,
|
| 96 |
+
"step": 13000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.74,
|
| 100 |
+
"learning_rate": 0.00017523051057428547,
|
| 101 |
+
"loss": 0.6933,
|
| 102 |
+
"step": 14000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.8,
|
| 106 |
+
"learning_rate": 0.00017346252544022655,
|
| 107 |
+
"loss": 0.6933,
|
| 108 |
+
"step": 15000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.85,
|
| 112 |
+
"learning_rate": 0.00017169277055127866,
|
| 113 |
+
"loss": 0.6932,
|
| 114 |
+
"step": 16000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9,
|
| 118 |
+
"learning_rate": 0.00016992478541721971,
|
| 119 |
+
"loss": 0.6933,
|
| 120 |
+
"step": 17000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.96,
|
| 124 |
+
"learning_rate": 0.00016815503052827185,
|
| 125 |
+
"loss": 0.6932,
|
| 126 |
+
"step": 18000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.01,
|
| 130 |
+
"learning_rate": 0.0001663870453942129,
|
| 131 |
+
"loss": 0.6932,
|
| 132 |
+
"step": 19000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.06,
|
| 136 |
+
"learning_rate": 0.000164617290505265,
|
| 137 |
+
"loss": 0.6933,
|
| 138 |
+
"step": 20000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.06,
|
| 142 |
+
"eval_accuracy": 0.4992196461142137,
|
| 143 |
+
"eval_loss": 0.6932681202888489,
|
| 144 |
+
"eval_runtime": 360.8474,
|
| 145 |
+
"eval_samples_per_second": 147.378,
|
| 146 |
+
"eval_steps_per_second": 18.423,
|
| 147 |
+
"step": 20000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.11,
|
| 151 |
+
"learning_rate": 0.00016284930537120612,
|
| 152 |
+
"loss": 0.6931,
|
| 153 |
+
"step": 21000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.17,
|
| 157 |
+
"learning_rate": 0.00016107955048225823,
|
| 158 |
+
"loss": 0.6933,
|
| 159 |
+
"step": 22000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.22,
|
| 163 |
+
"learning_rate": 0.00015931156534819928,
|
| 164 |
+
"loss": 0.6932,
|
| 165 |
+
"step": 23000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.27,
|
| 169 |
+
"learning_rate": 0.00015754181045925142,
|
| 170 |
+
"loss": 0.6932,
|
| 171 |
+
"step": 24000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.33,
|
| 175 |
+
"learning_rate": 0.00015577382532519247,
|
| 176 |
+
"loss": 0.6932,
|
| 177 |
+
"step": 25000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.38,
|
| 181 |
+
"learning_rate": 0.00015400407043624458,
|
| 182 |
+
"loss": 0.6931,
|
| 183 |
+
"step": 26000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.43,
|
| 187 |
+
"learning_rate": 0.00015223608530218565,
|
| 188 |
+
"loss": 0.6934,
|
| 189 |
+
"step": 27000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.49,
|
| 193 |
+
"learning_rate": 0.00015046633041323776,
|
| 194 |
+
"loss": 0.6932,
|
| 195 |
+
"step": 28000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.54,
|
| 199 |
+
"learning_rate": 0.00014869834527917884,
|
| 200 |
+
"loss": 0.6933,
|
| 201 |
+
"step": 29000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.59,
|
| 205 |
+
"learning_rate": 0.00014692859039023098,
|
| 206 |
+
"loss": 0.6933,
|
| 207 |
+
"step": 30000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.59,
|
| 211 |
+
"eval_accuracy": 0.5007803538857862,
|
| 212 |
+
"eval_loss": 0.6931193470954895,
|
| 213 |
+
"eval_runtime": 356.4083,
|
| 214 |
+
"eval_samples_per_second": 149.214,
|
| 215 |
+
"eval_steps_per_second": 18.653,
|
| 216 |
+
"step": 30000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.65,
|
| 220 |
+
"learning_rate": 0.00014516060525617203,
|
| 221 |
+
"loss": 0.6932,
|
| 222 |
+
"step": 31000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.7,
|
| 226 |
+
"learning_rate": 0.00014339085036722414,
|
| 227 |
+
"loss": 0.6932,
|
| 228 |
+
"step": 32000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.75,
|
| 232 |
+
"learning_rate": 0.00014162109547827628,
|
| 233 |
+
"loss": 0.6932,
|
| 234 |
+
"step": 33000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.81,
|
| 238 |
+
"learning_rate": 0.0001398513405893284,
|
| 239 |
+
"loss": 0.6932,
|
| 240 |
+
"step": 34000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.86,
|
| 244 |
+
"learning_rate": 0.00013808335545526944,
|
| 245 |
+
"loss": 0.6932,
|
| 246 |
+
"step": 35000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.91,
|
| 250 |
+
"learning_rate": 0.00013631360056632158,
|
| 251 |
+
"loss": 0.6932,
|
| 252 |
+
"step": 36000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.96,
|
| 256 |
+
"learning_rate": 0.00013454561543226263,
|
| 257 |
+
"loss": 0.6931,
|
| 258 |
+
"step": 37000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.02,
|
| 262 |
+
"learning_rate": 0.00013277586054331476,
|
| 263 |
+
"loss": 0.6932,
|
| 264 |
+
"step": 38000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.07,
|
| 268 |
+
"learning_rate": 0.00013100787540925584,
|
| 269 |
+
"loss": 0.6932,
|
| 270 |
+
"step": 39000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.12,
|
| 274 |
+
"learning_rate": 0.00012923812052030795,
|
| 275 |
+
"loss": 0.6933,
|
| 276 |
+
"step": 40000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.12,
|
| 280 |
+
"eval_accuracy": 0.5161429833963258,
|
| 281 |
+
"eval_loss": 0.6930696368217468,
|
| 282 |
+
"eval_runtime": 359.7266,
|
| 283 |
+
"eval_samples_per_second": 147.837,
|
| 284 |
+
"eval_steps_per_second": 18.481,
|
| 285 |
+
"step": 40000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.18,
|
| 289 |
+
"learning_rate": 0.000127470135386249,
|
| 290 |
+
"loss": 0.6932,
|
| 291 |
+
"step": 41000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.23,
|
| 295 |
+
"learning_rate": 0.00012570038049730114,
|
| 296 |
+
"loss": 0.6932,
|
| 297 |
+
"step": 42000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.28,
|
| 301 |
+
"learning_rate": 0.0001239323953632422,
|
| 302 |
+
"loss": 0.693,
|
| 303 |
+
"step": 43000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.34,
|
| 307 |
+
"learning_rate": 0.0001221626404742943,
|
| 308 |
+
"loss": 0.6932,
|
| 309 |
+
"step": 44000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.39,
|
| 313 |
+
"learning_rate": 0.00012039465534023538,
|
| 314 |
+
"loss": 0.6931,
|
| 315 |
+
"step": 45000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.44,
|
| 319 |
+
"learning_rate": 0.00011862490045128752,
|
| 320 |
+
"loss": 0.6932,
|
| 321 |
+
"step": 46000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.5,
|
| 325 |
+
"learning_rate": 0.00011685691531722858,
|
| 326 |
+
"loss": 0.6931,
|
| 327 |
+
"step": 47000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.55,
|
| 331 |
+
"learning_rate": 0.00011508716042828069,
|
| 332 |
+
"loss": 0.6932,
|
| 333 |
+
"step": 48000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.6,
|
| 337 |
+
"learning_rate": 0.00011331917529422176,
|
| 338 |
+
"loss": 0.6932,
|
| 339 |
+
"step": 49000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.65,
|
| 343 |
+
"learning_rate": 0.00011154942040527388,
|
| 344 |
+
"loss": 0.6931,
|
| 345 |
+
"step": 50000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.65,
|
| 349 |
+
"eval_accuracy": 0.4991068238656663,
|
| 350 |
+
"eval_loss": 0.6932998895645142,
|
| 351 |
+
"eval_runtime": 359.6843,
|
| 352 |
+
"eval_samples_per_second": 147.855,
|
| 353 |
+
"eval_steps_per_second": 18.483,
|
| 354 |
+
"step": 50000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.71,
|
| 358 |
+
"learning_rate": 0.00010978143527121494,
|
| 359 |
+
"loss": 0.6931,
|
| 360 |
+
"step": 51000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.76,
|
| 364 |
+
"learning_rate": 0.00010801168038226705,
|
| 365 |
+
"loss": 0.6931,
|
| 366 |
+
"step": 52000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.81,
|
| 370 |
+
"learning_rate": 0.00010624369524820812,
|
| 371 |
+
"loss": 0.6929,
|
| 372 |
+
"step": 53000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.87,
|
| 376 |
+
"learning_rate": 0.00010447571011414921,
|
| 377 |
+
"loss": 0.6931,
|
| 378 |
+
"step": 54000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.92,
|
| 382 |
+
"learning_rate": 0.00010270595522520132,
|
| 383 |
+
"loss": 0.6926,
|
| 384 |
+
"step": 55000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.97,
|
| 388 |
+
"learning_rate": 0.00010093620033625344,
|
| 389 |
+
"loss": 0.6914,
|
| 390 |
+
"step": 56000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.03,
|
| 394 |
+
"learning_rate": 9.916644544730555e-05,
|
| 395 |
+
"loss": 0.6929,
|
| 396 |
+
"step": 57000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.08,
|
| 400 |
+
"learning_rate": 9.740023006813557e-05,
|
| 401 |
+
"loss": 0.6932,
|
| 402 |
+
"step": 58000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.13,
|
| 406 |
+
"learning_rate": 9.563578444385452e-05,
|
| 407 |
+
"loss": 0.693,
|
| 408 |
+
"step": 59000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.19,
|
| 412 |
+
"learning_rate": 9.386602955490666e-05,
|
| 413 |
+
"loss": 0.6932,
|
| 414 |
+
"step": 60000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.19,
|
| 418 |
+
"eval_accuracy": 0.4991068238656663,
|
| 419 |
+
"eval_loss": 0.6932001709938049,
|
| 420 |
+
"eval_runtime": 363.5383,
|
| 421 |
+
"eval_samples_per_second": 146.287,
|
| 422 |
+
"eval_steps_per_second": 18.287,
|
| 423 |
+
"step": 60000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.24,
|
| 427 |
+
"learning_rate": 9.209627466595877e-05,
|
| 428 |
+
"loss": 0.693,
|
| 429 |
+
"step": 61000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.29,
|
| 433 |
+
"learning_rate": 9.032651977701089e-05,
|
| 434 |
+
"loss": 0.6931,
|
| 435 |
+
"step": 62000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.34,
|
| 439 |
+
"learning_rate": 8.8556764888063e-05,
|
| 440 |
+
"loss": 0.6912,
|
| 441 |
+
"step": 63000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.4,
|
| 445 |
+
"learning_rate": 8.678700999911514e-05,
|
| 446 |
+
"loss": 0.6923,
|
| 447 |
+
"step": 64000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.45,
|
| 451 |
+
"learning_rate": 8.50190248650562e-05,
|
| 452 |
+
"loss": 0.6864,
|
| 453 |
+
"step": 65000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.5,
|
| 457 |
+
"learning_rate": 8.324926997610831e-05,
|
| 458 |
+
"loss": 0.6833,
|
| 459 |
+
"step": 66000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.56,
|
| 463 |
+
"learning_rate": 8.148128484204938e-05,
|
| 464 |
+
"loss": 0.6827,
|
| 465 |
+
"step": 67000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.61,
|
| 469 |
+
"learning_rate": 7.97115299531015e-05,
|
| 470 |
+
"loss": 0.6778,
|
| 471 |
+
"step": 68000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.66,
|
| 475 |
+
"learning_rate": 7.794177506415362e-05,
|
| 476 |
+
"loss": 0.6766,
|
| 477 |
+
"step": 69000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.72,
|
| 481 |
+
"learning_rate": 7.617202017520573e-05,
|
| 482 |
+
"loss": 0.6746,
|
| 483 |
+
"step": 70000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.72,
|
| 487 |
+
"eval_accuracy": 0.5796054982042459,
|
| 488 |
+
"eval_loss": 0.6725409030914307,
|
| 489 |
+
"eval_runtime": 362.6905,
|
| 490 |
+
"eval_samples_per_second": 146.629,
|
| 491 |
+
"eval_steps_per_second": 18.33,
|
| 492 |
+
"step": 70000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.77,
|
| 496 |
+
"learning_rate": 7.440226528625786e-05,
|
| 497 |
+
"loss": 0.6729,
|
| 498 |
+
"step": 71000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.82,
|
| 502 |
+
"learning_rate": 7.263251039730997e-05,
|
| 503 |
+
"loss": 0.6683,
|
| 504 |
+
"step": 72000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.88,
|
| 508 |
+
"learning_rate": 7.08627555083621e-05,
|
| 509 |
+
"loss": 0.6649,
|
| 510 |
+
"step": 73000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.93,
|
| 514 |
+
"learning_rate": 6.909300061941421e-05,
|
| 515 |
+
"loss": 0.666,
|
| 516 |
+
"step": 74000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 3.98,
|
| 520 |
+
"learning_rate": 6.732324573046634e-05,
|
| 521 |
+
"loss": 0.6647,
|
| 522 |
+
"step": 75000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.04,
|
| 526 |
+
"learning_rate": 6.555349084151845e-05,
|
| 527 |
+
"loss": 0.6674,
|
| 528 |
+
"step": 76000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.09,
|
| 532 |
+
"learning_rate": 6.378550570745952e-05,
|
| 533 |
+
"loss": 0.6645,
|
| 534 |
+
"step": 77000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 4.14,
|
| 538 |
+
"learning_rate": 6.201575081851165e-05,
|
| 539 |
+
"loss": 0.6644,
|
| 540 |
+
"step": 78000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 4.19,
|
| 544 |
+
"learning_rate": 6.024599592956376e-05,
|
| 545 |
+
"loss": 0.6605,
|
| 546 |
+
"step": 79000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.25,
|
| 550 |
+
"learning_rate": 5.847624104061587e-05,
|
| 551 |
+
"loss": 0.6582,
|
| 552 |
+
"step": 80000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 4.25,
|
| 556 |
+
"eval_accuracy": 0.6032229555668378,
|
| 557 |
+
"eval_loss": 0.6613653898239136,
|
| 558 |
+
"eval_runtime": 359.5282,
|
| 559 |
+
"eval_samples_per_second": 147.919,
|
| 560 |
+
"eval_steps_per_second": 18.491,
|
| 561 |
+
"step": 80000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.3,
|
| 565 |
+
"learning_rate": 5.67100256614459e-05,
|
| 566 |
+
"loss": 0.6565,
|
| 567 |
+
"step": 81000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.35,
|
| 571 |
+
"learning_rate": 5.4942040527386965e-05,
|
| 572 |
+
"loss": 0.6561,
|
| 573 |
+
"step": 82000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.41,
|
| 577 |
+
"learning_rate": 5.317228563843908e-05,
|
| 578 |
+
"loss": 0.6562,
|
| 579 |
+
"step": 83000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.46,
|
| 583 |
+
"learning_rate": 5.14025307494912e-05,
|
| 584 |
+
"loss": 0.6558,
|
| 585 |
+
"step": 84000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.51,
|
| 589 |
+
"learning_rate": 4.963277586054332e-05,
|
| 590 |
+
"loss": 0.6553,
|
| 591 |
+
"step": 85000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.57,
|
| 595 |
+
"learning_rate": 4.786302097159544e-05,
|
| 596 |
+
"loss": 0.652,
|
| 597 |
+
"step": 86000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.62,
|
| 601 |
+
"learning_rate": 4.60950358375365e-05,
|
| 602 |
+
"loss": 0.6519,
|
| 603 |
+
"step": 87000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.67,
|
| 607 |
+
"learning_rate": 4.432528094858862e-05,
|
| 608 |
+
"loss": 0.6475,
|
| 609 |
+
"step": 88000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.73,
|
| 613 |
+
"learning_rate": 4.255552605964074e-05,
|
| 614 |
+
"loss": 0.6517,
|
| 615 |
+
"step": 89000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.78,
|
| 619 |
+
"learning_rate": 4.078754092558181e-05,
|
| 620 |
+
"loss": 0.6455,
|
| 621 |
+
"step": 90000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.78,
|
| 625 |
+
"eval_accuracy": 0.6132265282713751,
|
| 626 |
+
"eval_loss": 0.6466211676597595,
|
| 627 |
+
"eval_runtime": 358.035,
|
| 628 |
+
"eval_samples_per_second": 148.536,
|
| 629 |
+
"eval_steps_per_second": 18.568,
|
| 630 |
+
"step": 90000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 4.83,
|
| 634 |
+
"learning_rate": 3.901778603663393e-05,
|
| 635 |
+
"loss": 0.6411,
|
| 636 |
+
"step": 91000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 4.88,
|
| 640 |
+
"learning_rate": 3.7251570657463943e-05,
|
| 641 |
+
"loss": 0.6418,
|
| 642 |
+
"step": 92000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.94,
|
| 646 |
+
"learning_rate": 3.548181576851607e-05,
|
| 647 |
+
"loss": 0.6419,
|
| 648 |
+
"step": 93000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 4.99,
|
| 652 |
+
"learning_rate": 3.371206087956818e-05,
|
| 653 |
+
"loss": 0.6403,
|
| 654 |
+
"step": 94000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 5.04,
|
| 658 |
+
"learning_rate": 3.194407574550925e-05,
|
| 659 |
+
"loss": 0.6358,
|
| 660 |
+
"step": 95000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.1,
|
| 664 |
+
"learning_rate": 3.0176090611450313e-05,
|
| 665 |
+
"loss": 0.633,
|
| 666 |
+
"step": 96000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.15,
|
| 670 |
+
"learning_rate": 2.8406335722502436e-05,
|
| 671 |
+
"loss": 0.6315,
|
| 672 |
+
"step": 97000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 5.2,
|
| 676 |
+
"learning_rate": 2.6636580833554553e-05,
|
| 677 |
+
"loss": 0.6315,
|
| 678 |
+
"step": 98000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 5.26,
|
| 682 |
+
"learning_rate": 2.4866825944606673e-05,
|
| 683 |
+
"loss": 0.6284,
|
| 684 |
+
"step": 99000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 5.31,
|
| 688 |
+
"learning_rate": 2.309884081054774e-05,
|
| 689 |
+
"loss": 0.6256,
|
| 690 |
+
"step": 100000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 5.31,
|
| 694 |
+
"eval_accuracy": 0.6391004306049153,
|
| 695 |
+
"eval_loss": 0.6324899196624756,
|
| 696 |
+
"eval_runtime": 358.7004,
|
| 697 |
+
"eval_samples_per_second": 148.26,
|
| 698 |
+
"eval_steps_per_second": 18.534,
|
| 699 |
+
"step": 100000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 5.36,
|
| 703 |
+
"learning_rate": 2.1329085921599857e-05,
|
| 704 |
+
"loss": 0.6267,
|
| 705 |
+
"step": 101000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 5.42,
|
| 709 |
+
"learning_rate": 1.9561100787540926e-05,
|
| 710 |
+
"loss": 0.6261,
|
| 711 |
+
"step": 102000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 5.47,
|
| 715 |
+
"learning_rate": 1.7791345898593046e-05,
|
| 716 |
+
"loss": 0.6263,
|
| 717 |
+
"step": 103000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 5.52,
|
| 721 |
+
"learning_rate": 1.6021591009645165e-05,
|
| 722 |
+
"loss": 0.6233,
|
| 723 |
+
"step": 104000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.57,
|
| 727 |
+
"learning_rate": 1.4253605875586232e-05,
|
| 728 |
+
"loss": 0.6206,
|
| 729 |
+
"step": 105000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.63,
|
| 733 |
+
"learning_rate": 1.2483850986638352e-05,
|
| 734 |
+
"loss": 0.6205,
|
| 735 |
+
"step": 106000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 5.68,
|
| 739 |
+
"learning_rate": 1.071409609769047e-05,
|
| 740 |
+
"loss": 0.6173,
|
| 741 |
+
"step": 107000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 5.73,
|
| 745 |
+
"learning_rate": 8.944341208742588e-06,
|
| 746 |
+
"loss": 0.6188,
|
| 747 |
+
"step": 108000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 5.79,
|
| 751 |
+
"learning_rate": 7.178125829572605e-06,
|
| 752 |
+
"loss": 0.6193,
|
| 753 |
+
"step": 109000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 5.84,
|
| 757 |
+
"learning_rate": 5.408370940624724e-06,
|
| 758 |
+
"loss": 0.6144,
|
| 759 |
+
"step": 110000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.84,
|
| 763 |
+
"eval_accuracy": 0.6535040710028017,
|
| 764 |
+
"eval_loss": 0.6181166768074036,
|
| 765 |
+
"eval_runtime": 370.6733,
|
| 766 |
+
"eval_samples_per_second": 143.471,
|
| 767 |
+
"eval_steps_per_second": 17.935,
|
| 768 |
+
"step": 110000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 5.89,
|
| 772 |
+
"learning_rate": 3.638616051676843e-06,
|
| 773 |
+
"loss": 0.6189,
|
| 774 |
+
"step": 111000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 5.95,
|
| 778 |
+
"learning_rate": 1.8688611627289622e-06,
|
| 779 |
+
"loss": 0.6177,
|
| 780 |
+
"step": 112000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 6.0,
|
| 784 |
+
"learning_rate": 9.910627378108132e-08,
|
| 785 |
+
"loss": 0.6149,
|
| 786 |
+
"step": 113000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.0,
|
| 790 |
+
"step": 113010,
|
| 791 |
+
"total_flos": 1.40117450989583e+20,
|
| 792 |
+
"train_loss": 0.6729164371932674,
|
| 793 |
+
"train_runtime": 20561.1299,
|
| 794 |
+
"train_samples_per_second": 87.94,
|
| 795 |
+
"train_steps_per_second": 5.496
|
| 796 |
+
}
|
| 797 |
+
],
|
| 798 |
+
"logging_steps": 1000,
|
| 799 |
+
"max_steps": 113010,
|
| 800 |
+
"num_input_tokens_seen": 0,
|
| 801 |
+
"num_train_epochs": 6,
|
| 802 |
+
"save_steps": 10000,
|
| 803 |
+
"total_flos": 1.40117450989583e+20,
|
| 804 |
+
"train_batch_size": 16,
|
| 805 |
+
"trial_name": null,
|
| 806 |
+
"trial_params": null
|
| 807 |
+
}
|